ciso8601 converts ISO 8601 or RFC 3339 date time strings into Python datetime objects.

Since it's written as a C module, it is much faster than other Python libraries. Tested with cPython 2.7, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, 3.10, 3.11, 3.12, 3.13.

(Interested in working on projects like this? Close is looking for great engineers to join our team)

% pip install ciso8601

In [1]: import ciso8601

In [2]: ciso8601.parse_datetime('2014-12-05T12:30:45.123456-05:30')
Out[2]: datetime.datetime(2014, 12, 5, 12, 30, 45, 123456, tzinfo=pytz.FixedOffset(330))

In [3]: ciso8601.parse_datetime('20141205T123045')
Out[3]: datetime.datetime(2014, 12, 5, 12, 30, 45)

Version 2.0.0 of ciso8601 changed the core implementation. This was not entirely backwards compatible, and care should be taken when migrating See CHANGELOG for the Migration Guide.

ciso8601 is not necessarily the best solution for every use case (especially since Python 3.11). See Should I use ciso8601?

Starting in v2.0.0, ciso8601 offers strong guarantees when it comes to parsing strings.

parse_datetime(dt: String): datetime is a function that takes a string and either:

• Returns a properly parsed Python datetime, if and only if the entire string conforms to the supported subset of ISO 8601
• Raises a ValueError with a description of the reason why the string doesn't conform to the supported subset of ISO 8601

If time zone information is provided, an aware datetime object will be returned. Otherwise, a naive datetime is returned.

Parsing a timestamp with no time zone information (e.g., 2014-01-09T21:48:00):

ciso8601 takes 98 nsec, which is 1.3x faster than datetime (builtin), the next fastest Python 3.12 parser in this comparison.

Parsing a timestamp with time zone information (e.g., 2014-01-09T21:48:00-05:30):

ciso8601 takes 95 nsec, which is 2.1x faster than datetime (builtin), the next fastest Python 3.12 parser in this comparison.

Tested on Linux 5.15.49-linuxkit using the following modules:

aniso8601==9.0.1
arrow==1.3.0 (on Python 3.8, 3.9, 3.10, 3.11, 3.12), arrow==1.2.3 (on Python 3.7), arrow==0.17.0 (on Python 2.7)
backports.datetime_fromisoformat==2.0.1
ciso8601==2.3.0
iso8601==2.1.0 (on Python 3.8, 3.9, 3.10, 3.11, 3.12), iso8601==0.1.16 (on Python 2.7)
iso8601utils==0.1.2
isodate==0.6.1
maya==0.6.1
metomi-isodatetime==1!3.1.0
moment==0.12.1
pendulum==2.1.2
PySO8601==0.2.0
python-dateutil==2.8.2
str2date==0.905
udatetime==0.0.17
zulu==2.0.0

For full benchmarking details (or to run the benchmark yourself), see benchmarking/README.rst

ciso8601 only supports a subset of ISO 8601, but supports a superset of what is supported by Python itself (datetime.fromisoformat), and supports the entirety of the RFC 3339 specification.

The following date formats are supported:

Uncommon ISO 8601 date formats are not supported:

Times are optional and are separated from the date by the letter T.

Consistent with RFC 3339, ciso8601 also allows either a space character, or a lower-case t, to be used instead of a T.

The following time formats are supported:

Note: Python datetime objects only have microsecond precision (6 digits). Any additional precision will be truncated.

Time zone information may be provided in one of the following formats:

While the ISO 8601 specification allows the use of MINUS SIGN (U+2212) in the time zone separator, ciso8601 only supports the use of the HYPHEN-MINUS (U+002D) character.

Consistent with RFC 3339, ciso8601 also allows a lower-case z to be used instead of a Z.

ciso8601 parses ISO 8601 datetimes, which can be thought of as a superset of RFC 3339 (roughly). In cases where you might want strict RFC 3339 parsing, ciso8601 offers a parse_rfc3339 method, which behaves in a similar manner to parse_datetime:

parse_rfc3339(dt: String): datetime is a function that takes a string and either:

• Returns a properly parsed Python datetime, if and only if the entire string conforms to RFC 3339.
• Raises a ValueError with a description of the reason why the string doesn't conform to RFC 3339.

It takes more time to parse timestamps with time zone information, especially if they're not in UTC. However, there are times when you don't care about time zone information, and wish to produce naive datetimes instead. For example, if you are certain that your program will only parse timestamps from a single time zone, you might want to strip the time zone information and only output naive datetimes.

In these limited cases, there is a second function provided. parse_datetime_as_naive will ignore any time zone information it finds and, as a result, is faster for timestamps containing time zone information.

In [1]: import ciso8601

In [2]: ciso8601.parse_datetime_as_naive('2014-12-05T12:30:45.123456-05:30')
Out[2]: datetime.datetime(2014, 12, 5, 12, 30, 45, 123456)

NOTE: parse_datetime_as_naive is only useful in the case where your timestamps have time zone information, but you want to ignore it. This is somewhat unusual. If your timestamps don't have time zone information (i.e. are naive), simply use parse_datetime. It is just as fast.